用聚类路由替代传统检索，让小规模文档库更快更准。
MODE: Mixture of Document Experts for RAG
- 将文档聚类成语义簇，用中心点快速定位相关片段。
- 在100-500段落的库上，准确率媲美或超越基线，提速明显。
- 适合注重速度与领域聚焦的小中型知识库应用。
检索增强生成（RAG）通常依赖大规模向量数据库和针对海量语料微调的交叉编码器，这对小规模、领域特定的语料而言可能过于冗余。本文提出MODE（文档专家混合模型），一种轻量级替代方案：以聚类与路由检索取代细粒度最近邻搜索。文档经嵌入后被分组为语义一致的簇，并由缓存的中心点代表。查询时，仅路由至最相关的中心点，从对应簇内检索上下文，无需外部向量数据库或重排序，同时保持低延迟。在包含100-500个段落的HotpotQA与SQuAD数据集上，MODE在答案质量上达到或超过密集检索基线，且端到端检索时间显著降低。消融实验表明，聚类粒度与多簇路由可调控召回率与精确率权衡，更紧密的簇能提升下游任务准确率。MODE为小中型语料提供了一种兼顾简洁性、速度与主题聚焦的实用方案。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) often relies on large vector databases and cross-encoders tuned for large-scale corpora, which can be excessive for small, domain-specific collections. We present MODE (Mixture of Document Experts), a lightweight alternative that replaces fine-grained nearest-neighbor search with cluster-and-route retrieval. Documents are embedded, grouped into semantically coherent clusters, and represented by cached centroids. At query time, we route to the top centroid(s) and retrieve context only within those clusters, eliminating external vector-database infrastructure and reranking while keeping latency low. On HotpotQA and SQuAD corpora with 100-500 chunks, MODE matches or exceeds a dense-retrieval baseline in answer quality while reducing end-to-end retrieval time. Ablations show that cluster granularity and multi-cluster routing control the recall/precision trade-off, and that tighter clusters improve downstream accuracy. MODE offers a practical recipe for small and medium corpora where simplicity, speed, and topical focus matter.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。